Files
olp/lib/ir/openai-to-ir.mjs
T
taodengandClaude Opus 4.7 (noreply@anthropic.com) e2e67de23a feat(phase-1): land IR + plugin loader + server skeleton (D3)
Phase 1 Day 1. First executable code lands. Zero providers wired yet
(per ALIGNMENT.md "v0.1 ships 0 Enabled Providers"); the server starts
clean and POST /v1/chat/completions returns 503 with no_enabled_provider.

Files added:
  lib/ir/types.mjs            - IR v1.0 schema + validators (ADR 0003)
  lib/ir/openai-to-ir.mjs     - OpenAI Chat Completions to IR
  lib/ir/ir-to-openai.mjs     - IR chunks to OpenAI SSE / non-stream
  lib/providers/base.mjs      - Provider contract + validateProvider + ProviderError
  lib/providers/index.mjs     - Static empty registry stub (ADR 0002)
  server.mjs                  - HTTP listener with createOlpServer factory + main guard
  test-features.mjs           - 61 tests across 7 suites (IR / provider / HTTP)

Files modified:
  package.json - main and scripts.start/test added back; targets now exist.

Authority citations:
  IR fields and translation direction: ADR 0003 sections Decision and
    Translation direction model.
  Provider contract (9 fields): ADR 0002 section Provider contract v1.0
    interface.
  Entry surface routes (health, v1/models, v1/chat/completions): OLP v0.1
    spec section 4.1 single-protocol entry; ALIGNMENT.md Authority 2.
  Zero-Enabled-Providers behaviour: ALIGNMENT.md Provider Inventory.

Architectural decisions worth recording:
  1. server.mjs uses a createOlpServer factory plus an import.meta.url
     main guard. The factory returns an unbound http.Server; only the
     main-script invocation calls .listen(). Tests import the real
     server.mjs and exercise the real router. No parallel implementation
     in the test file.

     This pattern was a fold-in from the orchestration step. The initial
     sonnet draft put a top-level server.listen call in server.mjs, which
     forced test-features.mjs to reimplement the router inline (a false-
     confidence trap because the real server logic would never be tested).
     Refactored before reviewer dispatch.

  2. lib/providers/index.mjs ships an empty STATIC_REGISTRY array, not a
     placeholder with dummy entries. ALIGNMENT.md Provider Inventory says
     v0.1 ships zero Enabled Providers; the registry honors that exactly.
     Phase 1 Day 2 adds the first import (Anthropic) when its plugin lands.

  3. BadRequestError lives in openai-to-ir.mjs and ProviderError in
     base.mjs. Reviewer suggested relocating to a shared lib/errors.mjs
     once the count exceeds two; deferred to Phase 1 Day 2 to ship with
     the third typed error class.

  4. contractVersion: '1.0' on each provider plugin: not enforced at D3
     because no providers exist yet. Reviewer flagged for Phase 1 Day 2
     tightening when the first provider lands.

Reviewer chain (Iron Rule 10):
  Initial implementer: sonnet (general-purpose).
  Refactor (createOlpServer + main guard) by the orchestrator after
    catching the inline-router parallel-implementation issue.
  Fresh-context reviewer: opus (ecc:code-reviewer). Verdict
    APPROVE_WITH_MINOR.

Reviewer's two non-blocking findings folded in:
  F1: removed unused createServer import from test-features.mjs line 12,
      left over from the refactor.
  F2: replaced finish_reason value 'error' with 'stop' in both the
      streaming error chunk path (lib/ir/ir-to-openai.mjs line 72) and
      the non-streaming error aggregation path (lib/ir/ir-to-openai.mjs
      line 153). The 'error' value is not in OpenAI's documented
      finish_reason enum (stop / length / tool_calls / content_filter /
      function_call / null), so emitting it would violate ALIGNMENT.md
      Rule 2 (b). Provider errors are now surfaced via a top-level
      response.error object plus an inline content marker. The matching
      test assertion at test-features.mjs line 325 was updated to verify
      finish_reason stays within the OpenAI enum.

Note on the F2 fold-in:
  Reviewer pointed only at the streaming path (line 72). After applying
  that fix I ran grep across lib/ and test-features.mjs for the same
  invention pattern and caught a second hit at line 153 (non-streaming
  aggregation). This is the "fold-in must grep the full repo, not only
  the file the reviewer named" discipline from
  ~/.cc-rules/memory/feedback/evidence_first_under_speed_pressure.md.
  Both hits are fixed in this commit.

Verification:
  node --check on all 7 new files plus modified package.json plus
    server.mjs plus lib/ir/ir-to-openai.mjs - all clean.
  npm test - 61/61 pass in 209ms, no flakes, no skipped.
  OLP_PORT=14001 node server.mjs followed by curl /health returns
    proper JSON; curl /v1/models returns 200 empty list; server shuts
    down cleanly on signal.
  grep "finish_reason.*error" returns zero hits across lib/ and tests.

Co-Authored-By: Claude Opus 4.7 (noreply@anthropic.com)
2026-05-23 17:06:30 +10:00

203 lines
6.9 KiB
JavaScript

/**
* lib/ir/openai-to-ir.mjs — OpenAI Chat Completions → IR v1.0 translation
*
* Authority: ADR 0003 § "Translation direction model" and § "Required/Optional fields"
* Entry-surface authority: OpenAI Chat Completions API
* https://platform.openai.com/docs/api-reference/chat/create
*
* This is the entry adapter — the single point where an OpenAI-shaped request
* is normalized into the IR. Provider plugins never see the OpenAI shape;
* they receive only the IR (ADR 0003 § "IR is not exposed externally").
*/
import { IR_VERSION, validateIRRequest } from './types.mjs';
// ── Custom error ──────────────────────────────────────────────────────────
export class BadRequestError extends Error {
/** @param {string} message */
constructor(message) {
super(message);
this.name = 'BadRequestError';
this.statusCode = 400;
}
}
// ── Role normalization ────────────────────────────────────────────────────
/**
* OpenAI deprecated role='function' in favour of role='tool'.
* Per ADR 0003, IR supports system/user/assistant/tool.
* @param {string} role
* @returns {string}
*/
function normalizeRole(role) {
if (role === 'function') return 'tool';
return role;
}
// ── Message translation ───────────────────────────────────────────────────
/**
* @param {object} msg - an OpenAI message object
* @returns {import('./types.mjs').IRMessage}
*/
function translateMessage(msg) {
if (!msg || typeof msg !== 'object') {
throw new BadRequestError('Each message must be an object');
}
const irMsg = {
role: normalizeRole(msg.role),
content: msg.content ?? '',
};
// content can be null for tool/function calls in OpenAI shape — normalise to ''
if (irMsg.content === null) {
irMsg.content = '';
}
if (msg.name !== undefined) {
irMsg.name = String(msg.name);
}
if (msg.tool_call_id !== undefined) {
irMsg.tool_call_id = String(msg.tool_call_id);
}
// OpenAI also uses function_call (deprecated) — treat as equivalent to tool_calls
if (Array.isArray(msg.tool_calls) && msg.tool_calls.length > 0) {
irMsg.tool_calls = msg.tool_calls.map(tc => ({
id: tc.id,
type: 'function',
function: {
name: tc.function?.name ?? '',
arguments: tc.function?.arguments ?? '',
},
}));
} else if (msg.function_call && typeof msg.function_call === 'object') {
// Deprecated OpenAI function_call field — map to single tool_calls entry
irMsg.tool_calls = [{
id: `fc-${Date.now()}`,
type: 'function',
function: {
name: msg.function_call.name ?? '',
arguments: msg.function_call.arguments ?? '',
},
}];
}
return irMsg;
}
// ── Tool definitions ──────────────────────────────────────────────────────
/**
* @param {object[]} tools - OpenAI tools array
* @returns {import('./types.mjs').IRToolDefinition[]}
*/
function translateTools(tools) {
if (!Array.isArray(tools)) return [];
return tools.map((t, i) => {
if (t.type !== 'function' || !t.function) {
throw new BadRequestError(`tools[${i}]: only type='function' tools are supported in IR v1.0`);
}
return {
type: 'function',
function: {
name: t.function.name,
...(t.function.description !== undefined && { description: t.function.description }),
...(t.function.parameters !== undefined && { parameters: t.function.parameters }),
},
};
});
}
// ── Main translator ───────────────────────────────────────────────────────
/**
* Translates an OpenAI Chat Completions request body into IR v1.0.
*
* Throws BadRequestError on validation failure.
*
* @param {object} openAIRequest - parsed JSON body from POST /v1/chat/completions
* @returns {import('./types.mjs').IRRequest}
*/
export function openAIToIR(openAIRequest) {
if (!openAIRequest || typeof openAIRequest !== 'object') {
throw new BadRequestError('Request body must be a JSON object');
}
if (!openAIRequest.model || typeof openAIRequest.model !== 'string') {
throw new BadRequestError('Request body must include a non-empty "model" string');
}
if (!Array.isArray(openAIRequest.messages) || openAIRequest.messages.length === 0) {
throw new BadRequestError('Request body must include a non-empty "messages" array');
}
/** @type {import('./types.mjs').IRRequest} */
const ir = {
irVersion: IR_VERSION,
model: openAIRequest.model,
stream: openAIRequest.stream === true,
messages: openAIRequest.messages.map((m, i) => {
try {
return translateMessage(m);
} catch (e) {
throw new BadRequestError(`messages[${i}]: ${e.message}`);
}
}),
};
// Optional numeric fields — type-coerce if needed
if (openAIRequest.max_tokens !== undefined && openAIRequest.max_tokens !== null) {
const v = Number(openAIRequest.max_tokens);
if (!Number.isInteger(v) || v <= 0) {
throw new BadRequestError('max_tokens must be a positive integer');
}
ir.max_tokens = v;
}
if (openAIRequest.temperature !== undefined && openAIRequest.temperature !== null) {
const v = Number(openAIRequest.temperature);
if (isNaN(v) || v < 0 || v > 2) {
throw new BadRequestError('temperature must be a number in [0, 2]');
}
ir.temperature = v;
}
if (openAIRequest.top_p !== undefined && openAIRequest.top_p !== null) {
const v = Number(openAIRequest.top_p);
if (isNaN(v) || v < 0 || v > 1) {
throw new BadRequestError('top_p must be a number in [0, 1]');
}
ir.top_p = v;
}
if (openAIRequest.stop !== undefined && openAIRequest.stop !== null) {
if (typeof openAIRequest.stop !== 'string' && !Array.isArray(openAIRequest.stop)) {
throw new BadRequestError('stop must be a string or array of strings');
}
ir.stop = openAIRequest.stop;
}
if (openAIRequest.tools !== undefined && openAIRequest.tools !== null) {
ir.tools = translateTools(openAIRequest.tools);
}
if (openAIRequest.tool_choice !== undefined && openAIRequest.tool_choice !== null) {
ir.tool_choice = openAIRequest.tool_choice;
}
if (openAIRequest.response_format !== undefined && openAIRequest.response_format !== null) {
ir.response_format = openAIRequest.response_format;
}
// Validate the constructed IR — belt-and-suspenders
const { valid, errors } = validateIRRequest(ir);
if (!valid) {
throw new BadRequestError(`IR validation failed: ${errors.join('; ')}`);
}
return ir;
}